Abstract: In an approach to improve generating an analytic application embodiments generate an analytic application from an image. Embodiments determine an orientation, font size, and color of a text, wherein the text is selected from one or more texts that are part of a visualization from the image. Embodiments classify the text using semantic analysis having predetermined criteria to create a result. Furthermore, embodiments bind one or more columns from a dataset to the visualization using the result of the semantic analysis, and apply a selection identified using predetermined criteria, comprising sorting, filtering, grouping, and aggregating, to data of the visualization. Additionally, embodiments create a new color palette having a dominant color in the analytic application, wherein the dominant color is identified as a most recurring color in the visualization of the image, and apply the new color palette to the analytic application.

Abstract: In an approach to improve generating an analytic application embodiments generate an analytic application from an image. Embodiments determine an orientation, font size, and color of a text, wherein the text is selected from one or more texts that are part of a visualization from the image. Embodiments classify the text using semantic analysis having predetermined criteria to create a result. Furthermore, embodiments bind one or more columns from a dataset to the visualization using the result of the semantic analysis, and apply a selection identified using predetermined criteria, comprising sorting, filtering, grouping, and aggregating, to data of the visualization. Additionally, embodiments create a new color palette having a dominant color in the analytic application, wherein the dominant color is identified as a most recurring color in the visualization of the image, and apply the new color palette to the analytic application.

Abstract: In an approach to combining visualizations in a business analytic application, responsive to receiving a plurality of original visualizations from a user, one or more visualization groups are created. A strength score is calculated for each visualization group of the one or more visualization groups. Responsive to the strength score for each visualization group of the one or more visualization groups meeting a minimum threshold score, one or more recommended visualizations are generated, wherein the one or more recommended visualizations are combinations of the plurality of original visualizations. The one or more recommended visualizations are sent to the user.

Abstract: In an approach to combining visualizations in a business analytic application, responsive to receiving a plurality of original visualizations from a user, one or more visualization groups are created. A strength score is calculated for each visualization group of the one or more visualization groups. Responsive to the strength score for each visualization group of the one or more visualization groups meeting a minimum threshold score, one or more recommended visualizations are generated, wherein the one or more recommended visualizations are combinations of the plurality of original visualizations. The one or more recommended visualizations are sent to the user.

Abstract: Provided is a method for extracting features from an image of a dashboard. The method comprises detecting a position of one or more visualizations in an image of a dashboard. Each of the one or more visualizations is classified based on a type of object in the visualization. Features of the visualizations are extracted. The features include data points underlying the visualizations, one or more colors in the image, and text found in the image. An output array is generated based on the extracted features.